A clustering approach for topic filtering within systematic literature reviews

Weißer, Tim; Saßmannshausen, Till; Ohrndorf, Dennis; Burggräf, Peter; Wagner, Johannes

doi:10.1016/j.mex.2020.100831

Cited by 44 publications

(26 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Weißer et al. [59] leverage the power of data analytics (topic filtering and clustering) to identify key topics in a large amount of textual data. This approach may support the detection of relevant trends and preselection of papers for further review, and has gained momentum in recent years.…”

Section: Development Of Future Projections (Step One)mentioning

confidence: 99%

Lessons Learned from a Two-Round Delphi-based Scenario Study

2021

View full text Add to dashboard Cite

The Delphi technique is a suitable methodology for structuring group communication to answer current and prospective research questions within several rounds. The method is used in many disciplines and characterized by anonymity, iteration, controlled feedback, and statistical “group response” (Rowe & Wright, 2001). This technical paper presents practical details and lessons learned from a two-round Delphi-based scenario study in which projections (Delphi statements, questions or hypotheses) were developed with findings from expert interviews and an expert workshop. This Delphi study provides answers to future-related questions for which other research methods are inappropriate. This is depicted as a five-step process, making it easy to follow and replicable, for example to help first-time Delphi-method researchers. In doing so, the authors aim to provide the community with valuable technical insights and guidance for studies applying the Delphi technique both to prospective questions and in other research settings. Conducting a Delphi study can be a slow process with respect to receiving feedback from the panelists. Planning an appropriate period for distributing the questionnaire may produce a higher return rate. A sufficient time buffer should be incorporated into project planning. Projections that create dissent among the panelists may provide valuable results. Data analytics, software programs and online social networks can support researchers, save time and resources, and provide further insights in the process of conducting a Delphi study.

show abstract

Section: Development Of Future Projections (Step One)mentioning

confidence: 99%

Lessons Learned from a Two-Round Delphi-based Scenario Study

2021

View full text Add to dashboard Cite

show abstract

“…We employ the NLP-based clustering algorithm designed by Weißer et al [51]. This k-Means based algorithm uses tokenization (word separation), stop words removal and TFIDF vectorization to identify the most relevant words per cluster that describe its thematic relevance.…”

Section: Cluster Analysismentioning

confidence: 99%

Bibliometric Study on the Use of Machine Learning as Resolution Technique for Facility Layout Problems

2021

Self Cite

View full text Add to dashboard Cite

Facility Layout Problems (FLP) are concerned with finding efficient factory layouts. Numerous resolution approaches are known in literature for layout optimization. Among those, intelligent approaches are less researched than solutions from exact or approximating approaches. The recent surge of research interest in Artificial Intelligence, and specifically Machine Learning (ML) techniques, presages an increase of such techniques' usage in FLP. However, previous reviews on FLP research induce that, to date, this trend has not yet emerged. Utilizing a systematic literature review coupled with a k-Means based clustering algorithm, we analyzed 25 relevant publication full-texts from an original sample of 1,425 papers. Our findings corroborate the statement that ML techniques have attracted substantially less research interest than most other resolution approaches. While a few papers used Unsupervised Learning algorithms directly as a solution to the FLP, Supervised and Reinforcement Learning were found to be practically irrelevant. ML usage was significantly higher in FLP-adjacent planning tasks such as group technology. Drawing from experiences with other NP-hard combinatorial optimization problems in manufacturing research, we conclude that Reinforcement Learning is most promising to bridge the evident gap between FLP and ML research. Our study further contributes to FLP research by extending established classification frameworks.

show abstract

“…This finding indicates that the unemployment rate in Japan and the 2014); (Furlanetto & Groshenny, 2014); Sedláček (2014); (Schaal, 2012); (Chuma, 2002); (Azizah et al, 2015;Charles et al, 2013). Cramer (2010); and Saint-Paul ( 2005 Sources: Adapted from Okoli (2015); Weißer et al (2020); and Xiao & Watson (2019) United Kingdom is susceptible to economic growth; this is possibly because most of the population works in the formal sector, both manufacturing and service industries, which are the main booster of the GDP. This condition drives the labor markets in Japan and United Kingdom to be sensitive to the pace of economic growth.…”

Section: Granger Causality Testmentioning

confidence: 99%

The Unemployment Rate Amid the COVID-19 Pandemic: Propose the Best Practices Policy to Maintain Labor Market Stability

Malik

Suliswanto

Rofik

2021

JSP

View full text Add to dashboard Cite

This study analyzes the impact of the shocks caused by the COVID-19 pandemic on the labor market. The research is vital for expanding the literature about maintaining the unemployment rate amid crisis, ultimately reducing unnecessary social costs. The quantitative approach in this study uses a Granger causality test to understand the effect of the shock caused by the COVID-19 pandemic on unemployment. Meanwhile, the qualitative approach in this study uses literature related to economic growth, crisis management, and unemployment. Granger causality tests show that economic slowdown hurts the unemployment rate. Based on discussion and synthesis from works of literature, this paper recommends some of the policies to maintain growth and prevent a more severe collapse in the labor market; the government needs to sustain aggregate demand and supply. Also, ensure the supply chain runs well amid various restrictions. Besides, this paper also proposes that the government maximizes alternative budget resources. Meanwhile, strengthening the labor system and developing health and food security industries must be a priority policy amid-post the pandemic.

show abstract

A clustering approach for topic filtering within systematic literature reviews

Cited by 44 publications

References 8 publications

Lessons Learned from a Two-Round Delphi-based Scenario Study

Lessons Learned from a Two-Round Delphi-based Scenario Study

Bibliometric Study on the Use of Machine Learning as Resolution Technique for Facility Layout Problems

The Unemployment Rate Amid the COVID-19 Pandemic: Propose the Best Practices Policy to Maintain Labor Market Stability

Contact Info

Product

Resources

About